ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition

By Dipendra Jha, Logan T. Ward, Arindam Paul, W. Liao, Alok N. Choudhary, Chris Wolverton, Ankit Agrawal. Scientific Reports, 2018

460 citations recorded by the source corpus.

Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.

Subfields: Computational Theory and Mathematics, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/1b51a389a65cd13782254bfe5f36ea73b163151c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

Citations in the corpus

Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, methodology): “This approach was demonstrated in the context of material discovery in [338], [339].”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, background): “…a variety of chemical problems, including compound identiﬁcation and classiﬁcation, and description of soft matter behavior (Huang et al., 2018; Jha et al., 2018; Jørgensen et al., 2018b; Popova et al., 2018; Segler et al., 2018; Zhou et al., 2018; Chandrasekaran et al., 2019; Degiacomi, 2019;…”
Recent advances and applications of deep learning methods in materials science (2021, methodology): “It is relevant to note that ElemNet 141 , which is a 17-layer neural network composed of fully connected layers and uses only raw elemental fractions as input, was found to signi ﬁ cantly outperform traditional ML methods such as Random Forest, even when they were allowed to use more sophisticated p”
Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation (2020, methodology): “Actually, many of the good performance scores are due to the highly redundant or similar training samples in the dataset [18].”